Related papers: Can Broad Biomedical Knowledge be Contextualized i…

Evaluating multi-turn interactive agents is challenging due to the need for human assessment. Evaluation with simulated users has been introduced as an alternative, however existing approaches typically model generic users and overlook the…

We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through normalization, classification, extraction, or lightweight domain reasoning. Motivated…

Large Language Models (LLMs) have shown impressive capabilities in contextual understanding and reasoning. However, evaluating their performance across diverse scientific domains remains underexplored, as existing benchmarks primarily focus…

Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we…

Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn varying compositions of the same scene, our method reasons…

Biomedical imaging modalities often produce high-resolution, multi-dimensional images that pose computational challenges for deep neural networks. These computational challenges are compounded when training transformers due to the…

Existing dense retrieval models struggle with reasoning-intensive retrieval task as they fail to capture implicit relevance that requires reasoning beyond surface-level semantic information. To address these challenges, we propose…

Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications.…

Sketch semantic segmentation is a well-explored and pivotal problem in computer vision involving the assignment of pre-defined part labels to individual strokes. This paper presents ContextSeg - a simple yet highly effective approach to…

Knowledge graphs, collectively as a knowledge network, have become critical tools for knowledge discovery in computable and explainable knowledge systems. Due to the semantic and structural complexities of biomedical data, these knowledge…

Since scenes are composed in part of objects, accurate recognition of scenes requires knowledge about both scenes and objects. In this paper we address two related problems: 1) scale induced dataset bias in multi-scale convolutional neural…

Much of biomedical and healthcare data is encoded in discrete, symbolic form such as text and medical codes. There is a wealth of expert-curated biomedical domain knowledge stored in knowledge bases and ontologies, but the lack of reliable…

Medical image segmentation can provide a reliable basis for further clinical analysis and disease diagnosis. The performance of medical image segmentation has been significantly advanced with the convolutional neural networks (CNNs).…

Recently, the semantics of scene text has been proven to be essential in fine-grained image classification. However, the existing methods mainly exploit the literal meaning of scene text for fine-grained recognition, which might be…

Engineered image-based biomarkers offer a clinically interpretable alternative to black-box AI in computational pathology, yet their discovery remains largely intuition-driven, guided by fragmented literature rather than rigorous biological…

Representation learning provides new and powerful graph analytical approaches and tools for the highly valued data science challenge of mining knowledge graphs. Since previous graph analytical methods have mostly focused on homogeneous…

Here we present a holistic approach for data exploration on dense knowledge graphs as a novel approach with a proof-of-concept in biomedical research. Knowledge graphs are increasingly becoming a vital factor in knowledge mining and…

The problem of named entity recognition in the medical/clinical domain has gained increasing attention do to its vital role in a wide range of clinical decision support applications. The identification of complete and correct term span is…

Automatic vertebrae identification and localization from arbitrary CT images is challenging. Vertebrae usually share similar morphological appearance. Because of pathology and the arbitrary field-of-view of CT scans, one can hardly rely on…

Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where…